def voice_analysis():
print("Loading library...")
Vokaturi.load("../SIM/libs/OpenVokaturi-2-1/lib/Vokaturi_mac.so")
print("Analyzed by: %s" % Vokaturi.versionAndLicense())
print("Reading sound file...")
file_name = "demo.wav"
(sample_rate, samples) = scipy.io.wavfile.read(file_name)
print(" sample rate %.3f Hz" % sample_rate)
print("Allocating Vokaturi sample array...")
buffer_length = len(samples)
print(" %d samples, %d channels" % (buffer_length, samples.ndim))
c_buffer = Vokaturi.SampleArrayC(buffer_length)
if samples.ndim == 1: # mono
c_buffer[:] = samples[:] / 32768.0
else: # stereo
c_buffer[:] = 0.5 * (samples[:, 0] + 0.0 + samples[:, 1]) / 32768.0
print("Creating VokaturiVoice...")
voice = Vokaturi.Voice(sample_rate, buffer_length)
print("Filling VokaturiVoice with samples...")
voice.fill(buffer_length, c_buffer)
print("Extracting emotions from VokaturiVoice...")
quality = Vokaturi.Quality()
emotionProbabilities = Vokaturi.EmotionProbabilities()
voice.extract(quality, emotionProbabilities)
if quality.valid:
with Connection('amqp://*****:*****@localhost:5672//') as conn:
producer = conn.Producer(serializer='json')
producer.publish(
{
'Neutral': format(emotionProbabilities.neutrality, '.3f'),
'Happy': format(emotionProbabilities.happiness, '.3f'),
'Sad': format(emotionProbabilities.sadness, '.3f'),
'Angry': format(emotionProbabilities.anger, '.3f'),
'Fear': format(emotionProbabilities.fear, '.3f')
},
exchange=media_exchange,
routing_key='voice',
declare=[voice_queue])
# print ("Neutral: %.3f" % emotionProbabilities.neutrality)
# print ("Happy: %.3f" % emotionProbabilities.happiness)
# print ("Sad: %.3f" % emotionProbabilities.sadness)
# print ("Angry: %.3f" % emotionProbabilities.anger)
# print ("Fear: %.3f" % emotionProbabilities.fear)
else:
print("Not enough sonorancy to determine emotions")
voice.destroy()
def sentiment_analysis(path=sys.argv[1]):
print("Loading library...")
Vokaturi.load("./OpenVokaturi-3-0-linux64.so")
print("Analyzed by: %s" % Vokaturi.versionAndLicense())
print("Reading sound file...")
file_name = path
(sample_rate, samples) = scipy.io.wavfile.read(file_name)
print(" sample rate %.3f Hz" % sample_rate)
print("Allocating Vokaturi sample array...")
buffer_length = len(samples)
print(" %d samples, %d channels" % (buffer_length, samples.ndim))
c_buffer = Vokaturi.SampleArrayC(buffer_length)
if samples.ndim == 1:
c_buffer[:] = samples[:] / 32768.0 # mono
else:
c_buffer[:] = 0.5 * (samples[:, 0] + 0.0 +
samples[:, 1]) / 32768.0 # stereo
print("Creating VokaturiVoice...")
voice = Vokaturi.Voice(sample_rate, buffer_length)
print("Filling VokaturiVoice with samples...")
voice.fill(buffer_length, c_buffer)
print("Extracting emotions from VokaturiVoice...")
quality = Vokaturi.Quality()
emotionProbabilities = Vokaturi.EmotionProbabilities()
voice.extract(quality, emotionProbabilities)
if quality.valid:
print("Neutral: %.3f" % emotionProbabilities.neutrality)
print("Happy: %.3f" % emotionProbabilities.happiness)
print("Sad: %.3f" % emotionProbabilities.sadness)
print("Angry: %.3f" % emotionProbabilities.anger)
print("Fear: %.3f" % emotionProbabilities.fear)
out_dict = {}
out_dict['neutral'] = emotionProbabilities.neutrality
out_dict['happy'] = emotionProbabilities.happiness
out_dict['sad'] = emotionProbabilities.sadness
out_dict['angry'] = emotionProbabilities.anger
out_dict['fear'] = emotionProbabilities.fear
voice.destroy()
return out_dict
def main():
print("Loading library...")
Vokaturi.load("lib/open/win/OpenVokaturi-3-3-win64.dll")
print("Analyzed by: %s" % Vokaturi.versionAndLicense())
r = RedisManager(host=RedisConfig['host'],
port=RedisConfig['port'],
db=RedisConfig['db'],
password=RedisConfig['password'],
decodedResponses=RedisConfig['decodedResponses'])
sub = r.getRedisPubSub()
sub.subscribe(RedisConfig['newAudioPubSubChannel'])
for item in sub.listen():
print(item) # Test
if item['type'] == 'message':
newMsg = item['data']
print("New Msg: " + str(newMsg)) # Test
if not isinstance(newMsg, str):
newMsg = newMsg.decode()
audioID = newMsg
audioContent = r.hgetFromRedis(
key=audioID, field=RedisConfig['audioHsetB64Field'])
audioParams = r.hgetFromRedis(
key=audioID, field=RedisConfig['audioHsetParamsField'])
if audioContent:
if isinstance(audioParams, bytes):
audioParams = audioParams.decode('utf-8')
if isinstance(audioContent, bytes):
audioContent = audioContent.decode('utf-8')
audioContent = base64.b64decode(audioContent)
audioContent = ast.literal_eval(audioContent.decode('utf-8'))
audioParams = ast.literal_eval(audioParams)
audioEmotions = extractEmotionsFromAudioFile(
audioContent, audioParams)
print(audioEmotions) # Test
if not audioEmotions:
audioEmotions = RedisConfig['voidMsg']
r.publishOnRedis(channel=RedisConfig['VocalChannel'],
msg=str(audioEmotions))
r.hsetOnRedis(key=audioID,
field=RedisConfig['audioHsetVocalResultField'],
value=str(audioEmotions))
def analyzeAudio(filename):
print("Loading library...")
Vokaturi.load("lib/OpenVokaturi-3-3/lib/open/win/OpenVokaturi-3-3-win64.dll")
print("Analyzed by: %s" % Vokaturi.versionAndLicense())
print("Reading sound file...")
(sample_rate, samples) = scipy.io.wavfile.read(filename)
print(" sample rate %.3f Hz" % sample_rate)
print("Allocating Vokaturi sample array...")
buffer_length = len(samples)
print(" %d samples, %d channels" % (buffer_length, samples.ndim))
c_buffer = Vokaturi.SampleArrayC(buffer_length)
if samples.ndim == 1:
c_buffer[:] = samples[:] / 32768.0 # mono
else:
c_buffer[:] = 0.5*(samples[:,0]+0.0+samples[:,1]) / 32768.0 # stereo
print("Creating VokaturiVoice...")
voice = Vokaturi.Voice(sample_rate, buffer_length)
print("Filling VokaturiVoice with samples...")
voice.fill(buffer_length, c_buffer)
print("Extracting emotions from VokaturiVoice...")
quality = Vokaturi.Quality()
emotionProbabilities = Vokaturi.EmotionProbabilities()
voice.extract(quality, emotionProbabilities)
if quality.valid:
print("Neutral: %.3f" % emotionProbabilities.neutrality)
print("Happy: %.3f" % emotionProbabilities.happiness)
print("Sad: %.3f" % emotionProbabilities.sadness)
print("Angry: %.3f" % emotionProbabilities.anger)
print("Fear: %.3f" % emotionProbabilities.fear)
voice.destroy()
return emotionProbabilities
# For the sound file example.wav that comes with OpenVokaturi, the result should be:
# Neutral: 0.760
# Happy: 0.000
# Sad: 0.238
# Angry: 0.001
# Fear: 0.000
import sys
import scipy.io.wavfile
sys.path.append("../api")
import Vokaturi
print("Loading library...")
Vokaturi.load("../lib/Vokaturi_win64.dll")
print("Analyzed by: %s" % Vokaturi.versionAndLicense())
print("Reading sound file...")
file_name = sys.argv[1]
(sample_rate, samples) = scipy.io.wavfile.read(file_name)
print(" sample rate %.3f Hz" % sample_rate)
print("Allocating Vokaturi sample array...")
buffer_length = len(samples)
print(" %d samples, %d channels" % (buffer_length, samples.ndim))
c_buffer = Vokaturi.SampleArrayC(buffer_length)
if samples.ndim == 1: # mono
c_buffer[:] = samples[:] / 32768.0
else: # stereo
c_buffer[:] = 0.5 * (samples[:, 0] + 0.0 + samples[:, 1]) / 32768.0
#
# A sample script that uses the Vokaturi library to extract the emotions from
# a wav file on disk. The file has to contain a mono recording.
#
# Call syntax:
# python3 measure_wav_linux32.py path_to_sound_file.wav
import sys
import scipy.io.wavfile
sys.path.append("../api")
import Vokaturi
print ("Loading library...")
Vokaturi.load("../lib/Vokaturi_linux32.so")
print ("Analyzed by: %s" % Vokaturi.versionAndLicense())
print ("Reading sound file...")
file_name = sys.argv[1]
(sample_rate, samples) = scipy.io.wavfile.read(file_name)
print (" sample rate %.3f Hz" % sample_rate)
print ("Allocating Vokaturi sample array...")
buffer_length = len(samples)
print (" %d samples, %d channels" % (buffer_length, samples.ndim))
c_buffer = Vokaturi.SampleArrayC(buffer_length)
if samples.ndim == 1:
c_buffer[:] = samples[:] / 32768.0
else:
c_buffer[:] = 0.5*(samples[:,0]+0.0+samples[:,1]) / 32768.0
def getOS(self):
print("Analyzed by: %s" % Vokaturi.versionAndLicense())
def voice_predict():
file_name = "Audio/audio.wav"
print("Loading library...")
Vokaturi.load("OpenVokaturi-2-1d/lib/Vokaturi_mac64.so")
print("Analyzed by: %s" % Vokaturi.versionAndLicense())
print("Reading sound file...")
(sample_rate, samples) = scipy.io.wavfile.read(file_name)
print(" sample rate %.3f Hz" % sample_rate)
print("Allocating Vokaturi sample array...")
buffer_length = len(samples)
print(" %d samples, %d channels" % (buffer_length, samples.ndim))
c_buffer = Vokaturi.SampleArrayC(buffer_length)
if samples.ndim == 1:
c_buffer[:] = samples[:] / 32768.0 # mono
else:
c_buffer[:] = 0.5 * (samples[:, 0] + 0.0 +
samples[:, 1]) / 32768.0 # stereo
print("Creating VokaturiVoice...")
voice = Vokaturi.Voice(sample_rate, buffer_length)
print("Filling VokaturiVoice with samples...")
voice.fill(buffer_length, c_buffer)
print("Extracting emotions from VokaturiVoice...")
quality = Vokaturi.Quality()
emotionProbabilities = Vokaturi.EmotionProbabilities()
voice.extract(quality, emotionProbabilities)
fh = open("output.txt", 'a')
fh.write("Based on your voice, your emotion is ")
if not quality.valid:
fh.write("beyond my understanding.\n")
exit(1)
print_result = [(round(emotionProbabilities.neutrality*100), "neutral"), \
(round(emotionProbabilities.happiness*100), "happy"), \
(round(emotionProbabilities.anger*100), "angry"), \
(round(emotionProbabilities.fear*100),"fearful"), \
(round(emotionProbabilities.sadness*100), "sad")]
print_result = [tup for tup in print_result if tup[0] != 0]
print_result.sort(key=lambda tup: tup[0])
if len(print_result) == 0:
fh.write("beyond my understanding.\n")
elif len(print_result) == 1:
fh.write("dominantly %d percent %s.\n" %
(print_result[0][0], print_result[0][1]))
else:
for i in range(len(print_result) - 1, 0, -1):
fh.write("%d percent %s, " %
(print_result[i][0], print_result[i][1]))
fh.write("and %d percent %s.\n" %
(print_result[0][0], print_result[0][1]))
fh.close()
with open("output.txt") as f1:
with open("templates.yaml", "w") as f2:
f2.write("welcome: Ready to hear your comments?\n\nround: ")
for line in f1:
f2.write(line.strip("\n"))
f2.write(" ")
voice.destroy()
